Pranjalps1/Qwen3.5-2b-it-tool-full

VISIONConcurrent Unit Cost:1Model Size:2.3BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jun 22, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

Pranjalps1/Qwen3.5-2b-it-tool-full is a 2.3 billion parameter instruction-tuned Qwen3.5 model developed by Pranjalps1. This model was fine-tuned from Pranjalps1/Qwen3.5-2b-reasoning-full and optimized for faster training using Unsloth and Huggingface's TRL library. It is designed for general instruction-following tasks, leveraging its efficient training methodology.

Loading preview...

Model Overview

Pranjalps1/Qwen3.5-2b-it-tool-full is a 2.3 billion parameter instruction-tuned model, developed by Pranjalps1. It is based on the Qwen3.5 architecture and was fine-tuned from the Pranjalps1/Qwen3.5-2b-reasoning-full model. The training process for this iteration was notably accelerated, achieving 2x faster training speeds through the integration of Unsloth and Huggingface's TRL library.

Key Characteristics

  • Architecture: Qwen3.5 base model.
  • Parameter Count: 2.3 billion parameters.
  • Training Efficiency: Utilizes Unsloth and Huggingface TRL for significantly faster fine-tuning.
  • License: Released under the Apache-2.0 license.

Intended Use Cases

This model is suitable for various instruction-following applications where a compact yet capable language model is required. Its efficient training process suggests potential for rapid iteration and deployment in scenarios demanding quick fine-tuning cycles.